We propose a Cooperative Question Answering System that takes as input natural language queries and is able to return a cooperative answer based on semantic web resources, more specifically DBpedia represented in OWL/RDF as knowledge base and WordNet to build similar questions. Our system resorts to ontologies not only for reasoning but also to find answers and is independent of prior knowledge of the semantic resources by the user. The natural language question is translated into its semantic representation and then answered by consulting the semantics sources of information. The system is able to clarify the problems of ambiguity and helps finding the path to the correct answer. If there are multiple answers to the question posed (or to the similar questions for which DBpedia contains answers), they will be grouped according to their semantic meaning, providing a more cooperative and clarified answer to the user. 1. Introduction Ontologies and the semantic web  became a fundamental methodology to represent the conceptual domains of knowledge and to promote the capabilities of semantic question answering systems . These systems by allowing search in the structured large databases and knowledge bases of the semantic web can be considered as an alternative or as a complement to the current web search. There is a gap between users and the semantic web: it is difficult for end users to understand the complexity of the logic-based semantic web. Therefore, it is crucial to allow a common web user to profit from the expressive power of semantic web data models while hiding its potential complexity. There is a need for user-friendly interfaces that scale up to the web of data and support end-users in querying this heterogeneous information source. Consistent with the role played by ontologies in structuring semantic information on the web, ontology-based question answering systems allow us to exploit the expressive power of ontologies and go beyond the usual “keyword-based queries”. Question answering systems provide concise answers to natural language question posed by users in their own terminology . Those answers must also be in natural language in order to improve the system and provide a better user friendly interface. In this paper, we propose a cooperative question-answering system that receives queries expressed in natural language and is able to return a cooperative answer, also in natural language, obtained from resources on the semantic web (Ontologies and OWL2 Descriptions). The system starts a dialogue whenever there is some question
A. Andrenucci and E. Sneiders, “Automated question answering: review of the main approaches,” in Proceedings of the 3rd International Conference on Information Technology and Applications (ICITA '05), pp. 514–519, July 2005.
F. Benamara and P. Saint-Dizier, “Lexicalisation strategies in cooperative question-answering systems,” in Proceedings of the 20th International Conference on Computational Linguistics. Number Cruse 1986 in COLING '04, p. 1179, Association for Computational Linguistics, Stroudsburg, Pa, USA, 2004.
J. Wielemaker, M. Hildebrand, J. van Ossenbruggen, et al., “Using Prolog as the fundament for applications on the semantic web,” in Proceedings of the International Workshop on Applications of Logic Programming in the Semantic Web and Semantic Web Services (ALPSWS '07), pp. 84–98, 2007.
I. Rodrigues, L. Quintano, and L. Ferreira, “Nl database dialogue question-answering as a constraint satisfaction problem,” in Proceedings of the 18th International Conference on Applications of Declarative Programming and Knowledge Management (INAP '09), pp. 97–108, University of évora, 2009.